Skip to content

Benchmark

Horangi 4 subset: bigcodebench_100

Coding benchmarks compare models on programming tasks. Higher scores are better.

Models measured
79
Scores recorded
83
Sources
1
IQ weight
1.97

Score distribution

0.487
Mean
0.515
Median
0.11
Std dev
0.4
10th percentile
0.571
90th percentile
0.01
Min
0.010.68
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.97 for chat models, measured over 79 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51DeepSeek Reasonerdeepseek-v3.2: high-effort· Horangi Korean Leaderboard 4 data docs0.49
52Gemma 4 31B ITgemma-4-31B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.49
53GLM 5V Turboglm-5v-turbo· Horangi Korean Leaderboard 4 data docs0.49
54Mistral Medium 3.5mistral-medium-3-5· Horangi Korean Leaderboard 4 data docs0.49
55Nemotron 3 Nano 30B A3BNVIDIA-Nemotron-3-Nano-30B-A3B-BF16· Horangi Korean Leaderboard 4 data docs0.49
56Gemma 3 12B ITgemma-3-12b-it· Horangi Korean Leaderboard 4 data docs0.48
57Grok 4.1 Fastgrok-4-1-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.48
58MiMo V2 Promimo-v2-pro· Horangi Korean Leaderboard 4 data docs0.48
59MiMo V2 Flashmimo-v2-flash· Horangi Korean Leaderboard 4 data docs0.473
60GPT 4ogpt-4o-2024-11-20· Horangi Korean Leaderboard 4 data docs0.47
61Mistral Smallmistral-small-2603· Horangi Korean Leaderboard 4 data docs0.47
62Qwen3.5 9Bqwen3.5-9b· Horangi Korean Leaderboard 4 data docs0.465
63GPT-5 nanogpt-5-nano-2025-08-07· Horangi Korean Leaderboard 4 data docs0.46
64Qwen3 14BQwen3-14B· Horangi Korean Leaderboard 4 data docs0.46
65Qwen3.6 Flashqwen3.6-flash· Horangi Korean Leaderboard 4 data docs0.459
66Claude Haiku 4.5claude-haiku-4-5-20251001: high-effort· Horangi Korean Leaderboard 4 data docs0.45
67Gemma 3 27B ITgemma-3-27b-it· Horangi Korean Leaderboard 4 data docs0.45
68Grok 4 Fastgrok-4-fast-non-reasoning· Horangi Korean Leaderboard 4 data docs0.45
69GLM 4.7 Flashglm-4.7-flash· Horangi Korean Leaderboard 4 data docs0.44
70Qwen3 4B Instruct 2507Qwen3-4B-Instruct-2507· Horangi Korean Leaderboard 4 data docs0.44
71Qwen3 32BQwen3-32B· Horangi Korean Leaderboard 4 data docs0.42
72Qwen3 4BQwen3-4B· Horangi Korean Leaderboard 4 data docs0.42
73Qwen3 8BQwen3-8B· Horangi Korean Leaderboard 4 data docs0.42
74Grok 4.1 Fastgrok-4-1-fast-reasoning· Horangi Korean Leaderboard 4 data docs0.404
75Gemma 4 E4B-itgemma-4-E4B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.4
76Kimi K2.5kimi-k2.5· Horangi Korean Leaderboard 4 data docs0.374
77Gemma 4 E2B-itgemma-4-E2B-it: enable-thinking· Horangi Korean Leaderboard 4 data docs0.35
78Gemma 3 4B ITgemma-3-4b-it· Horangi Korean Leaderboard 4 data docs0.31
79GPT OSS 120Bgpt-oss-120b: high-effort· Horangi Korean Leaderboard 4 data docs0.3
80Qwen3 1.7BQwen3-1.7B· Horangi Korean Leaderboard 4 data docs0.22
81Gemma 3 1b itgemma-3-1b-it· Horangi Korean Leaderboard 4 data docs0.08
82Qwen3 0.6BQwen3-0.6B· Horangi Korean Leaderboard 4 data docs0.08
83Gemma 3 270M Itgemma-3-270m-it· Horangi Korean Leaderboard 4 data docs0.01

Showing 51–83 of 83 results.

Data credits: Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results